Taking decisions in the medical domain is a very complex task. The context is strongly affected by uncertainty and the possible undesired side effects of the treatments have to be carefully considered. Currently, these decisions are based on the physician's own experience and the evidences of the published literature, according, when available, with the philosophy of Evidence Based Medicine. The main issues of this approach are that the own experience can be different, and the results in the literature are sometimes contrasting. For helping physicians while taking medical decisions, we are proposing an innovative approach based on the idea of the clinical similarity. Given a set of clinical variables, the proposed approach selects patients that are similar, presenting to the physician the respective decisions taken and the corresponding clinical effects.