String　search　is　an　important　branch　of　pattern　matching　for　information　retrieval　in　various　fields.　In　the　past　four　decades,　the　research　importance　has　been　attached　on　skipping　more　unnecessary　characters　to　improve　the　search　performance,　and　never　taken　into　consideration　on　large　scale　of　data.　In　this　paper,　two　major　achievements　are　contributed.　At　first,　we　propose　a　Quick　Search　algorithm　for　data　Stream　(QSS)　on　a　single　machine　to　support　string　search　in　a　large　text　file,　as　opposed　to　previous　researches　that　limits　to　a　bound　memory.　For　the　next,　we　implement　the　search　algorithm　on　MapReduce　framework　to　improve　the　velocity　of　retrieving　the　search　results.　The　experiments　demonstrate　that　our　approach　is　fast　and　effective　for　large　files.