Increased exposure of the colon to bile acids, as a result of increased eating frequency, might promote the development of colon cancer. Our aim was to evaluate the association between eating frequency and colon cancer. We used data from a population-based case-control study of colon cancer in North Carolina. Eating frequency (a combination of meals and snacks) was categorized as fewer than three, three or four, or more than four eating episodes per day. Multivariate logistic regression was used to calculate odds ratios (ORs) for the association between eating frequency and colon cancer, adjusting for confounders. We also performed stratified analyses to evaluate for differences by sex, coffee intake, or tumor site. Six hundred thirty-six participants with colon cancer and 1,048 control participants were included. The effect of eating frequency on colon cancer differed by sex. Among men, participants in the lowest group of eating frequency had approximately half the risk of colon cancer compared with the middle group (adjusted OR = 0.53; 95% confidence interval, CI = 0.30-0.92). Compared with the middle group, men in the highest group had no greater risk of cancer (adjusted OR = 1.03; 95% CI = 0.74-1.44). No significant associations were detected among women. Decreased eating frequency was associated with a lower risk of colon cancer among men but not women.