有人發現嗎?MSSQL中的一個費解的問題

select * from table1 WHERE 
SUBSTRING(field1,3,2) IN ('G1','G2','G3','G4','G5','G6','G7','G8','G9','P1','P2','P3','P4','P5','P6','P7','P8','P9','W1','W2')查詢速度就超慢了,如果用19個來查詢速度才1秒,這個
'G1','G2','G3','G4','G5','G6','G7','G8','G9','P1','P2','P3','P4','P5','P6','P7','P8','P9','W1','W2'
用時 1分20秒'G1','G2','G3','G4','G5','G6','G7','G8','G9','P1','P2','P3','P4','P5','P6','P7','P8','P9','W1'
用時 1-2秒這個現像大家有遇到過嗎? 差1個可選項的查詢,速度差了這麼多.....為什麼?
我研究過和 in 沒有關係, 應該和substring 有關係.