Castor is an unilingual phrases database. Its role is to help you create groups of documents to be translated together: if they contain lot of common or similar segments in the source, your CAT tool will offer lot of auto-insertion of 100% matches.

Usually, Castor is not to be used during a translation but before :

1. When you send your document, it is analyzed (via Spongiae) and inserted segment by segment in the database;
2. You will receive a report saying whenever some documents have been found with a significant number of similar segments

Do not forget to delete documents which have already been translated (unless you kept the corresponding project in your CAT tool and want to re-use it): those documents should already be present in a long-term translation memory!

Actually the tool is based on exact similarity, meaning that you find only phrases which exist in multiple documents, i.e. 100 % matches (except for tags, which are not retrieved). Such segments are auto-inserted in most CAT tools. In the future fuzzy matches may also be considered, then the scoring rules may change.