It is very difficult to find and collect nursing diagnoses in hospitals, where various clinical records and procedures are done by hand and manually stored on paper form. This condition impairs the readability of hospital process documents, and the archival method makes the information recovery very slow, which ultimately frustrates the search which could result in important information to improve the decision making process. The aim of this paper is to present an application to help the nurses in the clinical reasoning, keeping their experiences as a collection of cases for future research. The process is to scan diagnoses of pediatric nursing, and insert them into a case database, in a structure that provides for recovery, adaptation, indexing and comparison of cases, to be used to evaluate the effectiveness of the prototype application in handling these cases. This article presents a computational tool for health care support, employing techniques of case based reasoning, whose performance was satisfactory in the location of cases directly related to the presented test case. This fact suggests that the prototype presented is able to recover diagnoses made previously and it is of great importance for decision-making and improvement of diagnoses. © 2009 PICMET.