A valuable source of field diagnostic information for equipment service resides in the text notes generated during service calls. Intelligent knowledge extraction from such textual information is a challenging task. The notes are typically characterized by misspelled words, incomplete information, cryptic technical terms, and nonstandard abbreviations, in addition, very few of the total number of notes generated may be diagnostically useful. A tool for identifying diagnostically relevant notes from the many raw field service notes and information is presented in this paper. N-gram matching and supervised learning techniques are used to generate recommendations for the diagnostic significance of incoming service notes. After some preprocessing and cleaning of the text, these diagnostic notes are indexed and made available in a laptop based tool to provide relevant retrieval in response to user queries and to help solve the current service call.