Background The prevalence of smoking in nursing personnel remains high. The aim of this study was to identify work factors that predict smoking cessation among nurses' aides. Methods Of 2720 randomly selected, Norwegian nurses' aides, who were smoking at least one cigarette per day when they completed a questionnaire in 1999, 2275 (83.6 %) completed a second questionnaire 15 months later. A wide spectrum of work factors were assessed at baseline. Respondents who reported smoking 0 cigarettes per day at follow-up were considered having stopped smoking. The odds ratios and 95 % confidence intervals of stopping smoking were derived from logistic regression models. Results Compared with working 1–9 hours per week, working 19–36 hours per week (odds ratio (OR) = 0.35; 95 % confidence interval (CI) = 0.13 – 0.91), and working more than 36 hours per week (i.e. more than full-time job) (OR = 0.27; CI = 0.09 – 0.78) were associated with reduced odds of smoking cessation, after adjustments for daily consumption of cigarettes at baseline, age, gender, marital status, and having preschool children. Adjusting also for chronic health problems gave similar results. Conclusion There seems to be a negative association between hours of work per week and the odds of smoking cessation in nurses' aides. It is important that health institutions offer workplace-based services with documented effects on nicotine dependence, such as smoking cessation courses, so that healthcare workers who want to stop smoking, especially those with long working hours, do not have to travel to the programme or to dedicate their leisure time to it.