Background: Pancreatic cancer (PC) is the fourth leading cause of cancer death in the United States, with PC-related mortality of over 36,000 in 2010. The etiology of PC remains elusive. An association with diabetes mellitus (DM) has been suggested, but due to the inconsistencies of the epidemiologic studies addressing this association, a consensus has not been reached. Evidence is rising for hyperinsulinemia, which exists in Type II DM, as a risk factor for developing PC. We have studied the incidence of PC in two large cohorts of patients with and without Type II DM. Methods: This is a retrospective cohort study utilizing the health-care database maintained by the Veterans Integrated Services Network 16 (VISN16), which consists of 10 Veterans Health Administration (VHA) hospitals in the south-central USA. The two cohorts of the study consisted of a DM cohort of patients diagnosed with Type II DM between October 1st, 1996 and September 30th, 2006, and a control cohort of non-diabetics matched to DM patients by year of birth (YOB), gender, and VHA hospital. After 365 required cancer-free days on study, members of both cohorts were followed for the development of PC. Incidence during follow-up was compared between groups via stratified Cox regression with year of birth, gender, and VHA hospital as the stratification factors. Results: 322,614 subjects met inclusion criteria, including 110,919 DM subjects and 211,695 controls. Cohorts remained well-matched for gender (2.3% females in each) and YOB (medians of 1939 in each). The DM cohort had 124 PCs develop during 0.558 million person-years (MPY) of follow-up (222 PCs/MPY), whereas the control cohort had 140 PCs develop during 1.299 MPY of follow-up (108 PCs/MPY). Stratified Cox regression of PC incidence yielded a hazard ratio (95% CI) of 2.17 (1.70–2.77) for Type II DM compared to controls (chi-square =38.9, DF=1, P<10^-9). Conclusions: This is one of the largest studies to examine the incidence of PC in patients with Type II DM. It shows a significantly higher incidence of PC in patients with DM. This study would provide a strong support for the etiologic role of DM II and hyperinsulinemia in the pathogenesis of PC.